# iMoonLab/yolov13

Implementation of "YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception".

Repository: https://github.com/iMoonLab/yolov13
Canonical: https://ross.abutalabs.com/products/yolov13
Language: Python
License: AGPL-3.0
License Family: copyleft
Topics: hypergraph-learning, object-detection, yolo, yolov13, correlation-modelling, real-time-object-detection, visual-recognition
Last push: 2025-11-18T11:12:30+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 52, release rhythm 8, longevity 31
- inputs: {"age_days": 438, "days_push": 288, "days_rel": 437, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1702, forks 177 (observed 2026-08-28T04:05:24.363030+00:00)

## What it is
Official PyTorch implementation of YOLOv13, a real-time object detection model family (Nano to X-Large) featuring Hypergraph-based Adaptive Correlation Enhancement (HyperACE). It supports training, validation, prediction, and model export for deployment on edge and mobile platforms.

## Use cases
- train a custom YOLOv13 object detection model on my own dataset
- run real-time object detection on images and video
- export YOLOv13 weights to ONNX, RKNN, or Ascend OM for edge deployment
- benchmark YOLOv13 against other YOLO versions on MS COCO
- deploy object detection on Android with ncnn
- serve detections via a FastAPI REST API

## When to choose
- you need state-of-the-art real-time object detection with high-order feature correlation modeling
- you want official weights, training code, and export tooling for the YOLOv13 paper
- you are deploying detection models to edge devices like Rockchip NPUs or Android

## When to avoid
- you need a permissively licensed model for commercial closed-source products (AGPL-3.0)
- you need a long-established, battle-tested detector like YOLOv8 instead of a newly released architecture
- your project does not involve object detection

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, computer-vision, image-processing
- domain: computer-vision, deep-learning, machine-learning
- platform: python, windows
- tags: yolo, object-detection, hypergraph-learning, real-time-inference, pytorch, model-training, model-export, gpu, linux, macos

## Member repositories
- iMoonLab/yolov13 (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:24.363030+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:37:40.406856+00:00, confidence not recorded.
  - readme: https://github.com/iMoonLab/yolov13 (fetched 2026-08-28T04:05:24.363030+00:00, sha 44f94628ff0e)
- Data as of 2026-08-30T08:39:29.467469+00:00.